mobilenet过程记录

1. 量化

1.1 浮点表示，参考 https://www.cnblogs.com/HDK2016/p/10506083.html

1.2 量化原理，参考
https://zhuanlan.zhihu.com/p/149659607
https://jackwish.net/2019/neural-network-quantization-introduction-chn.html

1.3 量化论文，参考：
(1) Google, Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference, https://arxiv.org/abs/1712.05877v1
(2) Intel, INQ, https://github.com/Ewenwan/Incremental-Network-Quantization
(3) IBM, PACT, https://arxiv.org/abs/1805.06085
(4) LSQ, https://blog.csdn.net/nature553863/article/details/104275477
(5) https://github.com/Yang-YiFan/DiracDeltaNet

2. MobileNet v1

2.1 源码，https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py

2.2 预训练模型, https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.md

附录

1. python学习记录，https://www.cnblogs.com/eesf/p/14551164.html